Fetch evidence documents for one campaign. Required input: campaign_id. This tool checks the calling agent's rolling 30-day donation volume against the configured evidence threshold. If the agent is not eligible yet, it returns a structured response with eligibility_status, total_30d, and evidenc...
Part of the Zooidfund server.
Free to start. No card required.
AI agents call get_evidence to retrieve information from Zooidfund without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_evidence only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"get_evidence": {}
}
}See the full Zooidfund policy for all 8 tools.
These attack patterns abuse exactly the kind of access get_evidence gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Fetch evidence documents for one campaign. Required input: campaign_id. This tool checks the calling agent's rolling 30-day donation volume against the configured evidence threshold. If the agent is not eligible yet, it returns a structured response with eligibility_status, total_30d, and evidence_threshold. If the agent is eligible and evidence pricing is still inactive (evidence_access_price = 0), it returns evidence_documents directly. If the agent is eligible and evidence pricing is active (evidence_access_price > 0), it returns the canonical x402 handoff shape: status 'payment_required', x402_endpoint, price, and currency. Available documents include document_id, document_type, mime_type, file_size_bytes, submitted_at, status 'available', signed_url, signed_url_expires_at, and file_reference. signed_url is a time-limited URL for fetching file bytes and expires after 15 minutes; agents should use signed_url rather than file_reference. Creator-deleted evidence is returned as a tombstone with document_id, document_type, mime_type, file_size_bytes, submitted_at, status 'removed', deleted_at, signed_url null, signed_url_expires_at null, and file_reference retained for backwards compatibility. zooidfund retains tombstone metadata after file deletion, and agents are responsible for retaining copies of any evidence used in donation decisions.. It is categorised as a Read tool in the Zooidfund MCP Server, which means it retrieves data without modifying state.
Register the Zooidfund MCP server in PolicyLayer and add a rule for get_evidence: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Zooidfund. Nothing to install.
get_evidence is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_evidence rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_evidence. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_evidence is provided by the Zooidfund MCP server (https://fcefnmdlggldmfusydix.supabase.co/functions/v1/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Zooidfund tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.